arXiv (All)
open access
Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards
Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Correcting this mismatch with learner-to-behavior importance weights can introduce high variance for long responses. We introduce Gibbs-Gap Policy Optimi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Lexicographic Multi-Objective On-Policy Distillation#1186673
- Metropolis-Hastings Dominates Importance Resampling for Policy Composition#1188158
- Metropolis-Hastings Dominates Importance Resampling for Policy Composition#1181654
- NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents#1118091
- Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization#1344235
Record · ID 1355803
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive